Groups in online social networks witness continuous evolution by loss of existing members and gain of new members. In this paper, we present a study of group split in Meetup, where a major fraction of members leave the existing group together and join a newly formed group. We identify pivotal group members, called splitters, playing key roles in group split by influencing the existing members to leave the group. We provide an in-depth analysis of the empirical data to reveal key motivating factors leading to a group split and its subsequent impact. Finally, we develop a prediction model for early detection of splitters, as well as the group members likely to be influenced by the splitter to leave the group.